© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69365
    Prev
    Next
    INDEX
    Explanations

    boot payload, binding, dt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     \
    -1.45
    }=
    -1.43
     usual
    -1.42
    .='
    -1.38
    erweise
    -1.38
    ogues
    -1.31
    isierung
    -1.29
     в
    -1.29
    +/**
    -1.28
     {
    -1.27
    POSITIVE LOGITS
     cómoda
    1.43
     acoged
    1.34
    ZAS
    1.28
     inmueble
    1.27
     delicada
    1.27
    leute
    1.27
     artesanales
    1.26
    躥
    1.25
    ّه
    1.25
     πριν
    1.24
    Activations Density 0.027%

    No Known Activations